Loading Events

« All Events

  • This event has passed.

DataFest 2019: 2-day Wine Catalog Challenge

December 12, 2019 @ 10:30 am - December 13, 2019 @ 4:00 pm

Contribute, learn and win a prize at the Fall 2019 DataFest (2-day hackathon) in the Library!

Complete this form to register for the DataFest.

WHAT IS A DataFest?

DataFests, Datathons, and Hackathons are events where you can flex your skills to make rapid progress on a research challenge. We provide the general problem and data, and you work in small teams to explore, develop and test interesting technical approaches and solutions. These events support concentrated time for hands-on practice applying data science tools, methods and computational reasoning, and are also a great way to build community, network and seed a portfolio project. Individuals from all domains, career stages and skill levels are welcSpatiaome to participate! Recruit your friends to come work with you on a team, or we’ll help you form one at the event. (Non-Davis students, Alumni, community members, or members from other UCs and CSU should contact us regarding space availability.)


Sherry Lehmann is a well-known and established seller of wine and spirits. The UC Davis Library has over 200 scanned catalogs spanning nearly a 50 year period. How do we translate a scanned image into usable data for economists, historians, archivists, and other researchers? Our previous Summer 2018 DataFest focused on extracting wine names and prices from a subset of the OCR’d catalogs. Now, we want more! What other information can we extract from these semi-structured pages?

Past, current and future aspects of this overall research project have included: OCR (optical character recognition), text processing, spatial reasoning, database access, crowd-sourced data, computer vision, statistical and machine learning methods, and most of all – common sense and creative problem solving!


This 2-day DataFest is held on December 12-13 from 10:30am-4pm each day. We kick off on Thursday with an information session to orient you to the overall research problem and your specific challenge, followed with time to form project teams. The remaining time on Thursday and most of Friday is devoted to collaborative hands-on work. There is time structured for report-outs for everyone to provide feedback and help, and a final showcase presentation which will precede the awards. We will provide coffee, tea, snacks and lunch to keep you going. All participants are expected to work in the DataLab classroom (Shields 360) for the entirety of the DataFest days, but you aren’t restricted to working on the project only during those times!


DataFests are a great opportunity to:

* contribute to important, relevant data science projects
* develop teamwork skills
* practice workflow best-practices
* problem solve!

There are many ways to contribute – across different subtasks and at all skill levels – so don’t be shy! Everyone is welcome and the strongest teams often have the most diverse backgrounds and perspectives!


At the end of the DataFest each team will present a short summary of their findings to the other teams and a panel of judges comprised of relevant staff and faculty. Teams will be judged based on their creativity, insight, and communication. Separate prizes will be awarded for technical solutions and conceptual approaches, so everyone – regardless of incoming skills – has a chance to succeed.


December 12, 2019 @ 10:30 am
December 13, 2019 @ 4:00 pm
Event Categories: